CODEWITHSUNDEEP
pythonseleniumweb-scrapingscrapy
Noob Gamer
Noob Gamer

Reputation: 55

Looping Urls in scrapy with selenium

I want to load the all url using loop and trying to get data from it But i am not unable to do. Somebody have any ideas how to deal multiple urls in scrapy.

Here is my code:

    import scrapy
from selenium import webdriver
from selenium.webdriver.chrome.options import Options
from shutil import which
from scrapy.selector import Selector
import time
from scrapy.http import Request

class TrSpider(scrapy.Spider):
    name = 'tr'
    allowed_domains = ['trc.com']
    start_urls = ['https://www.google.com/travel/things-to-do?g2lb=2502548,2503806,4258168,4270442,4306835,4317915,4328159,4371334,4401769,4419364,4463263,4463666,4464463,4482194,4482438,4486153,4270859,4284970,4291517&hl=en-PK&gl=pk&un=1&dest_mid=/m/0rtv&dest_state_type=main&sa=X&ved=2ahUKEwjvk6PXqLXuAhWN2BQKHZs1BNsQhdIBegQIARAW',
'https://www.google.com/travel/things-to-do?g2lb=2502548,2503806,4258168,4270442,4306835,4317915,4328159,4371334,4401769,4419364,4463263,4463666,4464463,4482194,4482438,4486153,4270859,4284970,4291517&hl=en-PK&gl=pk&un=1&dest_mid=/m/012gg6&dest_state_type=main&sa=X&ved=2ahUKEwjvk6PXqLXuAhWN2BQKHZs1BNsQhdIBegQIARAc',
'https://www.google.com/travel/things-to-do?g2lb=2502548,2503806,4258168,4270442,4306835,4317915,4328159,4371334,4401769,4419364,4463263,4463666,4464463,4482194,4482438,4486153,4270859,4284970,4291517&hl=en-PK&gl=pk&un=1&dest_mid=/m/027f5q&dest_state_type=main&sa=X&ved=2ahUKEwjvk6PXqLXuAhWN2BQKHZs1BNsQhdIBegQIARAi',
'https://www.google.com/travel/things-to-do?g2lb=2502548,2503806,4258168,4270442,4306835,4317915,4328159,4371334,4401769,4419364,4463263,4463666,4464463,4482194,4482438,4486153,4270859,4284970,4291517&hl=en-PK&gl=pk&un=1&dest_mid=/m/02d4_q&dest_state_type=main&sa=X&ved=2ahUKEwjvk6PXqLXuAhWN2BQKHZs1BNsQhdIBegQIARAo',
'https://www.google.com/travel/things-to-do?g2lb=2502548,2503806,4258168,4270442,4306835,4317915,4328159,4371334,4401769,4419364,4463263,4463666,4464463,4482194,4482438,4486153,4270859,4284970,4291517&hl=en-PK&gl=pk&un=1&dest_mid=/m/0b1nv7&dest_state_type=main&sa=X&ved=2ahUKEwjvk6PXqLXuAhWN2BQKHZs1BNsQhdIBegQIARAu',
'https://www.google.com/travel/things-to-do?g2lb=2502548,2503806,4258168,4270442,4306835,4317915,4328159,4371334,4401769,4419364,4463263,4463666,4464463,4482194,4482438,4486153,4270859,4284970,4291517&hl=en-PK&gl=pk&un=1&dest_mid=/m/04m7fh&dest_state_type=main&sa=X&ved=2ahUKEwjvk6PXqLXuAhWN2BQKHZs1BNsQhdIBegQIARA0',
'https://www.google.com/travel/things-to-do?g2lb=2502548,2503806,4258168,4270442,4306835,4317915,4328159,4371334,4401769,4419364,4463263,4463666,4464463,4482194,4482438,4486153,4270859,4284970,4291517&hl=en-PK&gl=pk&un=1&dest_mid=/m/0b95m1&dest_state_type=main&sa=X&ved=2ahUKEwjvk6PXqLXuAhWN2BQKHZs1BNsQhdIBegQIARA6',
'https://www.google.com/travel/things-to-do?g2lb=2502548,2503806,4258168,4270442,4306835,4317915,4328159,4371334,4401769,4419364,4463263,4463666,4464463,4482194,4482438,4486153,4270859,4284970,4291517&hl=en-PK&gl=pk&un=1&dest_mid=/m/0b95tg&dest_state_type=main&sa=X&ved=2ahUKEwjvk6PXqLXuAhWN2BQKHZs1BNsQhdIBegQIARBA',
'https://www.google.com/travel/things-to-do?g2lb=2502548,2503806,4258168,4270442,4306835,4317915,4328159,4371334,4401769,4419364,4463263,4463666,4464463,4482194,4482438,4486153,4270859,4284970,4291517&hl=en-PK&gl=pk&un=1&dest_mid=/m/02p77j&dest_state_type=main&sa=X&ved=2ahUKEwjvk6PXqLXuAhWN2BQKHZs1BNsQhdIBegQIARBG']

    def __init__(self):
        chrome_option = Options()
        chrome_option.add_argument('--headless')

        chrome_path = which('chromedriver')

        driver = webdriver.Chrome(executable_path=chrome_path)

        for a in self.start_urls:
            driver.get(a)
            driver.find_element_by_xpath('//button[@class="VfPpkd-LgbsSe VfPpkd-LgbsSe-OWXEXe-INsAgc VfPpkd-LgbsSe-OWXEXe-dgl2Hf Rj2Mlf OLiIxf PDpWxe J3Eqid"]').click()
            time.sleep(1)
            self.html = driver.page_source

    def parse(self, response):
        ab = response.url
        resp = Selector(text = self.html)
        
        for a in resp.xpath('//div[@class="GwjAi "]'):
            yield{
                'Name': a.xpath('./div[1]/div/text()').get(),
                'Rating': a.xpath('./div[2]/span/span/span[1]/text()').get(),
                'Number of reviews': a.xpath('./div[2]/span/span/span[2]/text()').get(),
                'Discription': a.xpath('./div[3]/text()').extract(),
                'Url': ab
            }

If I run with out looping it working but it will not working with multiple links. Thanks

Upvotes: 0

Views: 236

Answers (1)

SIM
SIM

Reputation: 22440

Try the following:

import scrapy
from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
from scrapy.selector import Selector
from selenium.common.exceptions import TimeoutException

class TrSpider(scrapy.Spider):
    name = 'tr'
    start_urls = [
        'https://www.google.com/travel/things-to-do?g2lb=2502548,2503806,4258168,4270442,4306835,4317915,4328159,4371334,4401769,4419364,4463263,4463666,4464463,4482194,4482438,4486153,4270859,4284970,4291517&hl=en-PK&gl=pk&un=1&dest_mid=/m/0rtv&dest_state_type=main&sa=X&ved=2ahUKEwjvk6PXqLXuAhWN2BQKHZs1BNsQhdIBegQIARAW',
        'https://www.google.com/travel/things-to-do?g2lb=2502548,2503806,4258168,4270442,4306835,4317915,4328159,4371334,4401769,4419364,4463263,4463666,4464463,4482194,4482438,4486153,4270859,4284970,4291517&hl=en-PK&gl=pk&un=1&dest_mid=/m/012gg6&dest_state_type=main&sa=X&ved=2ahUKEwjvk6PXqLXuAhWN2BQKHZs1BNsQhdIBegQIARAc',
        'https://www.google.com/travel/things-to-do?g2lb=2502548,2503806,4258168,4270442,4306835,4317915,4328159,4371334,4401769,4419364,4463263,4463666,4464463,4482194,4482438,4486153,4270859,4284970,4291517&hl=en-PK&gl=pk&un=1&dest_mid=/m/027f5q&dest_state_type=main&sa=X&ved=2ahUKEwjvk6PXqLXuAhWN2BQKHZs1BNsQhdIBegQIARAi',
        'https://www.google.com/travel/things-to-do?g2lb=2502548,2503806,4258168,4270442,4306835,4317915,4328159,4371334,4401769,4419364,4463263,4463666,4464463,4482194,4482438,4486153,4270859,4284970,4291517&hl=en-PK&gl=pk&un=1&dest_mid=/m/02d4_q&dest_state_type=main&sa=X&ved=2ahUKEwjvk6PXqLXuAhWN2BQKHZs1BNsQhdIBegQIARAo',
        'https://www.google.com/travel/things-to-do?g2lb=2502548,2503806,4258168,4270442,4306835,4317915,4328159,4371334,4401769,4419364,4463263,4463666,4464463,4482194,4482438,4486153,4270859,4284970,4291517&hl=en-PK&gl=pk&un=1&dest_mid=/m/0b1nv7&dest_state_type=main&sa=X&ved=2ahUKEwjvk6PXqLXuAhWN2BQKHZs1BNsQhdIBegQIARAu',
        'https://www.google.com/travel/things-to-do?g2lb=2502548,2503806,4258168,4270442,4306835,4317915,4328159,4371334,4401769,4419364,4463263,4463666,4464463,4482194,4482438,4486153,4270859,4284970,4291517&hl=en-PK&gl=pk&un=1&dest_mid=/m/04m7fh&dest_state_type=main&sa=X&ved=2ahUKEwjvk6PXqLXuAhWN2BQKHZs1BNsQhdIBegQIARA0',
        'https://www.google.com/travel/things-to-do?g2lb=2502548,2503806,4258168,4270442,4306835,4317915,4328159,4371334,4401769,4419364,4463263,4463666,4464463,4482194,4482438,4486153,4270859,4284970,4291517&hl=en-PK&gl=pk&un=1&dest_mid=/m/0b95m1&dest_state_type=main&sa=X&ved=2ahUKEwjvk6PXqLXuAhWN2BQKHZs1BNsQhdIBegQIARA6',
        'https://www.google.com/travel/things-to-do?g2lb=2502548,2503806,4258168,4270442,4306835,4317915,4328159,4371334,4401769,4419364,4463263,4463666,4464463,4482194,4482438,4486153,4270859,4284970,4291517&hl=en-PK&gl=pk&un=1&dest_mid=/m/0b95tg&dest_state_type=main&sa=X&ved=2ahUKEwjvk6PXqLXuAhWN2BQKHZs1BNsQhdIBegQIARBA',
        'https://www.google.com/travel/things-to-do?g2lb=2502548,2503806,4258168,4270442,4306835,4317915,4328159,4371334,4401769,4419364,4463263,4463666,4464463,4482194,4482438,4486153,4270859,4284970,4291517&hl=en-PK&gl=pk&un=1&dest_mid=/m/02p77j&dest_state_type=main&sa=X&ved=2ahUKEwjvk6PXqLXuAhWN2BQKHZs1BNsQhdIBegQIARBG'
    ]

    def start_requests(self):
        driver = webdriver.Chrome()
        wait = WebDriverWait(driver,10)
        for item_link in self.start_urls:
            driver.get(item_link)
            try:
                button = wait.until(EC.presence_of_element_located((By.XPATH, "//span[contains(.,'See all top sights')]")))
                driver.execute_script("arguments[0].click();",button)
            except TimeoutException:
                pass
            htmlelements = driver.page_source
            wait.until(EC.staleness_of(button))
            yield scrapy.Request(item_link,meta={"htmlelements":htmlelements})

    def parse(self, response):
        ab = response.url
        resp = Selector(text=response.meta.get("htmlelements"))
        for a in resp.xpath('//div[starts-with(@class,"GwjAi")]'):
            yield {
                'Name': a.xpath('./div[1]/div/text()').get(),
                'Rating': a.xpath('./div[2]/span/span/span[1]/text()').get(),
                'Number of reviews': a.xpath('./div[2]/span/span/span[2]/text()').get(),
                'Discription': a.xpath('./div[3]/text()').extract(),
                'Url': ab
            }

Upvotes: 1

Related Questions